Research map / Label-efficient and robust learning / Semi-supervised learning
Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch
Hyuck Lee, Taemin Park, Heeyoung Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LLA in the training phase (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 85.1 -> 90.4 | Improved |
| add LLA at test time (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 88.8 -> 90.4 | Improved |
| add LLA in both training and test (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 82.8 -> 90.4 | Improved |
| add EFCC in training (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 85.5 -> 90.4 | Improved |
| use learnable LLA instead of original LA (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 62.3 -> 90.4 | Improved |
| use extended EFCC instead of original FCC (ablation) | ReMixMatch+LLA · CIFAR-10-LT (γl=100, γu=1) | bACC: 75.5 -> 90.4 | Improved |
| add LLA to FixMatch | FixMatch · CIFAR-10-LT (γl=γu=100) | bACC: 71.5 -> 84.8 | Improved |
| add LLA to ReMixMatch | ReMixMatch · CIFAR-10-LT (γl=γu=100) | bACC: 73.8 -> 85.8 | Improved |
| add LLA to FixMatch | FixMatch · Small-ImageNet-127 (32x32) | bACC: 29.7 -> 52.2 | Improved |
| use LLA instead of CDMAD | ReMixMatch · CIFAR-10-LT (γl=100, γu=1) | bACC: 89.9 -> 90.4 | Improved |
| add LLA to FixMatch | FixMatch · CIFAR-100-LT (γ=100) | bACC: 37.6 -> 44.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 5 of 5 shared results
- ReMixMatch — ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring (ICLR 2020) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · similarity 0.87)
- CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (CVPR 2024 · similarity 0.87)
- Robust Logit Adjustment for Learning with Long-Tailed Noisy Data (AAAI 2025 · similarity 0.86)
- BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.86)
- Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning (AAAI 2025 · similarity 0.86)
- Improved Balanced Classification with Theoretically Grounded Loss Functions (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
